© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11332
    Prev
    Next
    INDEX
    Explanations

    mentions related to political unity

    oai_token-act-pair · gpt-3.5-turbo

    references to texture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Robbins
    -0.71
     broch
    -0.67
     Roy
    -0.65
     Cohn
    -0.65
     Robo
    -0.65
     Four
    -0.64
     Cooper
    -0.62
    hof
    -0.62
     Seven
    -0.62
     Rodgers
    -0.61
    POSITIVE LOGITS
    Magikarp
    1.01
     rul
    0.90
    ILA
    0.84
    tein
    0.82
    yip
    0.81
    ãĤ«
    0.77
    Reviewer
    0.77
    METHOD
    0.73
    alion
    0.72
    Discussion
    0.71
    Activations Density 0.000%

    No Known Activations